Qdrant Retrive MCP Server

MCP server for semantic search with Qdrant vector database

Local serverstdio

What is the Qdrant Retrive MCP server?

MCP server for semantic search with Qdrant vector database. That is what the qdrant retrive mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Options --enableHttpTransport Enable HTTP transport [default: false] --enableStdioTransport Enable stdio transport [default: true] --enableRestServer Enable REST API server [default: false] --mcpHttpPort= Port for MCP HTTP server [default: 3001] --restHttpPort= Port for REST HTTP server [default: 3002] --qdrantUrl= URL for Qdrant vector database [default: http://localhost:6333] --embeddingModelType= Type of embedding model to use [default: Xenova/all-MiniLM-L6-v2] --help Show this help message

  • Semantic search across multiple collections
  • Multi-query support
  • Configurable result count
  • Collection source tracking

The tools it exposes

The server publishes 8 tools. What each one is for:

  • qdrant_retrieve — Retrieves semantically similar documents from multiple Qdrant vector store collections based on multiple queries
  • Inputs — - collectionNames (string[]): Names of the Qdrant collections to search across
  • Returns — - results: Array of retrieved documents with:
  • query — The query that produced this result
  • collectionName — Collection name that this result came from
  • text — Document text content
  • score — Similarity score between 0 and 1
  • Tools — The Tools tool exposed by this server

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What it needs from you

Configuration is passed through the environment: QDRANT_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Qdrant Retrive's toolset — qdrant_retrieve, Inputs, Returns and 5 more — is a fair guide to whether it matches your workflow. It is maintained by gergelyszerovay; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
qdrant_retrieveRetrieves semantically similar documents from multiple Qdrant vector store collections based on multiple queries
Inputs- collectionNames (string[]): Names of the Qdrant collections to search across
Returns- results: Array of retrieved documents with:
queryThe query that produced this result
collectionNameCollection name that this result came from
textDocument text content
scoreSimilarity score between 0 and 1
ToolsThe Tools tool exposed by this server.

How to install the Qdrant Retrive MCP server

{
  "mcpServers": {
    "qdrant": {
      "command": "npx",
      "args": ["-y", "@gergelyszerovay/mcp-server-qdrant-retrive"],
      "env": {
        "QDRANT_API_KEY": "your_api_key_here"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
QDRANT_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Qdrant Retrive to qdrant retrieve.
  • Use Qdrant Retrive to Inputs.
  • Use Qdrant Retrive to Returns.

Frequently asked questions

It connects Qdrant Retrive to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (qdrant_retrieve, Inputs, Returns, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Qdrant Retrive directly.